PhD - Bridging the Gap between Model Predictive Control and Reinforcement Learning for Safety-critical Control

Company Description

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: We grow together, we enjoy our work, and we inspire each other. Welcome to Bosch.

The Robert Bosch GmbH is looking forward to your application!

Job Description

Learning-based control methodologies are rapidly gaining importance in academia and industry, despite the long-standing use of classical control engineering methods in practical applications. The main driving forces are improved performance, applicability to more complex planning tasks, and reduced manual design effort.
Despite the numerous learning-based control strategies suggested within the reinforcement learning field, safety remains a challenge in dynamic systems. Asymptotic stability, inherent robustness, and consistent constraint satisfaction are essential requirements for delivering dependable and high-quality products, particularly in the field of autonomous driving.
Your research aims at combining control engineering methods used for safety-critical systems, like model predictive control, with the emerging strategies in computer science, particularly reinforcement learning.
This combination offers benefits such as reducing online computational complexity, more efficient design computations, and improving control performance while maintaining safety standards.

Potential steps toward this goal include:

• Investigate and improve explicit approximations of predictive controllers and their relations to reinforcement learning strategies.
• Extend existing formulations regarding inherent robustness, modeling errors, and changing objectives.
• Verification of your results using real-world applications, e.g., within the field of autonomous driving.
• Contributing to leading academic conferences and publication of your results in leading journals.

Qualifications

• Education: excellent Master’s degree in Control Engineering, Computer Science, Electrical Engineering, Physics, Mathematics or comparable
• Personality and Working Practice: pursuing a successful Ph.D. in this interdisciplinary field requires thinking outside the box

Additional Information

https://www.bosch-ai.com
www.bosch.com/research

Please submit all relevant documents (incl. curriculum vitae, certificates).

You want to work remotely or part-time - we offer great opportunities for mobile working as well as different part-time models or job-sharing. Feel free to contact us.

Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore, we welcome all applications, regardless of gender, age, disability, religion, ethnic origin or sexual identity.

Need support during your application?
Kevin Heiner (Human Resources)
+49 711 8111 2223

Need further information about the job?
Kim Wabersich (Functional Department)
KimPeter.Wabersich@de.bosch.com